transition from add_tailor(prop) and method to fit.workflow(calibration)
#262
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
workflows will no longer take an `add_tailor(prop)` or `add_tailor(method)` argument, instead taking a `fit.workflow(calibration)` argument that supersedes both of them. first, remove machinery that relates specifically to those arguments.
…bration)` * removes `add_tailor(prop)` and `add_tailor(method)` * adds `fit.workflow(calibration)` * various documentation updates
simonpcouch
commented
Sep 27, 2024
hfrick
approved these changes
Sep 30, 2024
| #' | ||
| #' @param ... Not used | ||
| #' | ||
| #' @param calibration A data frame of predictors and outcomes to use when |
There was a problem hiding this comment.
I'm wondering if we should adapt the name slightly to make it more obvious that this the data for calibration, rather than, say, the method. data_calibration, calibration_data, calibration_set?
There was a problem hiding this comment.
Sure! I don't have strong preferences between any of these options, but agree that calibration by itself could be ambiguous.
| @@ -59,7 +59,7 @@ | |||
| #' datasets, resulting in the preprocessor and model generating predictions on | |||
| #' rows they've seen before. Similarly problematic situations could arise in the | |||
| #' context of other resampling situations, like time-based splits. | |||
| #' In general, use the [rsample::inner_split()] function to prevent data | |||
| #' In general, use the `rsample::inner_split()` function to prevent data | |||
There was a problem hiding this comment.
Same comment about inner_split() being "internal" or not
* edits to `validate_has_calibration()`:
* refer to "The workflow" rather than `caller_arg()`
* Warn rather than error on unneeded calibration set
* All arguments on one line in function signature
* comment on expectation re: predictions
* doc tweaks
* `.should_inner_split()` -> `.workflow_includes_calibration()` * refactor conditional in `fit.workflow()` into two
This was referenced Sep 30, 2024
|
This pull request has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Closes #255, closes #254, closes #252, closes #233, and related to this gist.
This PR removes the
add_tailor(prop)andmethodarguments in favor of an argumentfit.workflow(calibration)giving the data to fit the calibrator on.Benefits:
methodwasn't actually enough)add_tailor(method)really wasn't truly independent of the data/resampling schemeThanks @hfrick for this suggestion—this feels much better.
This PR should be much easier to review commit-by-commit than altogether.
TODOs from here: update tune and (possibly?) rename
.should_inner_split()to something like.workflow_needs_calibration().